Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ěl
    -0.07
    Unary
    -0.07
    (serial
    -0.06
     PCs
    -0.06
     Workers
    -0.06
    pm
    -0.06
    ätz
    -0.06
    #Region
    -0.06
     humiliating
    -0.06
    bred
    -0.06
    POSITIVE LOGITS
    :Boolean
    0.08
     usleep
    0.07
    .Fl
    0.06
    .IOException
    0.06
    _RECE
    0.06
     ironically
    0.06
    �
    0.06
     defenseman
    0.06
     upon
    0.06
    <Option
    0.06
    Act Density 0.134%

    No Known Activations